by TwillAI · MCP Server · ★ 166
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
npm install agentbox-sdkTaken from the project's README on GitHub.
None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours.
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 166 |
| Forks | 18 |
| Language | TypeScript |
| Category | MCP Server |
| Quality Score | 74/100 |
| Open Issues | 6 |
| Last Updated | 2026-10-14 |
| Created | 2025-05-15 |
| Platforms | mcp, node |
| Est. Tokens | ~16k |
AgentBox Run coding agents inside sandboxes. One API, any provider. Unlike wrappers that shell out to CLIs in non-interactive mode (e.g. ), AgentBox launches each agent as a server process inside the sandbox and communicates over WebSocket or HTTP. This preserves the full interactive capabilities of each agent — approval flows, tool-use control, streaming events.
Looking for a agentbox-sdk alternative? If you're comparing agentbox-sdk with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
An introduction to the world of AI Agents
Ultimate Context Engineering Infrastructure, starting from MCPs and Integrations
Your personal AI assistant, running on your own computer. Long-running tasks, real memory, proactive help, voi
Shell and coding agent on mcp clients
The open context engine for AI agents support 15+ data sources. Built on Rust and Apache DataFusion.
🚀 Universal SDK for building next-gen MCP servers
Explore other popular mcp server tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: